© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 77309
    Prev
    Next
    INDEX
    Explanations

    instances of the word "repeatedly" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aliyet
    -0.07
    uri
    -0.07
    arrant
    -0.07
    aign
    -0.07
    ÑĪкÑĥ
    -0.06
     повин
    -0.06
    ëĿ¼ëıĦ
    -0.06
    تاب
    -0.06
    arch
    -0.06
    alk
    -0.06
    POSITIVE LOGITS
    ly
    0.08
    ively
    0.07
     throughout
    0.07
    LY
    0.07
    TL
    0.06
    DCF
    0.06
    -use
    0.06
    以æĿ¥
    0.06
    Throughout
    0.06
    snd
    0.06
    Activations Density 0.013%

    No Known Activations